© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119536
    Prev
    Next
    INDEX
    Explanations

    specific points in time

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects words referring to brief time intervals (e.g. “moment,” “pause,” “fleeting,” “momentarily”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .”
    -2.58
     pezzo
    -2.19
     pacchetto
    -2.16
     soggiorno
    -2.09
     merav
    -2.03
    憮
    -2.00
     paziente
    -2.00
     nemici
    -1.93
     vettore
    -1.93
     she
    -1.93
    POSITIVE LOGITS
     «
    2.45
     ("
    2.34
    '
    2.33
     "
    2.31
     ''
    2.25
    (
    2.25
     («
    1.96
     (?)
    1.91
     reposo
    1.91
    法國
    1.88
    Activations Density 0.016%

    No Known Activations